© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31283
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESL
    -0.08
     свет
    -0.08
     גל
    -0.08
     ladan
    -0.08
     verd
    -0.08
     quirky
    -0.07
     belt
    -0.07
     blade
    -0.07
    (operator
    -0.07
     verdi
    -0.07
    POSITIVE LOGITS
     क्योंकि
    0.08
     Violence
    0.07
    .gu
    0.07
     Because
    0.07
    But
    0.07
    0.07
    inth
    0.07
               ↵
    0.07
     Viol
    0.07
     getan
    0.07
    Activations Density 0.000%

    No Known Activations